tcp: avoid premature drops in tcp_add_backlog()

[ Upstream commit ec00ed472bdb7d0af840da68c8c11bff9f4d9caa ]

While testing TCP performance with latest trees,
I saw suspect SOCKET_BACKLOG drops.

tcp_add_backlog() computes its limit with :

    limit = (u32)READ_ONCE(sk->sk_rcvbuf) +
            (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
    limit += 64 * 1024;

This does not take into account that sk->sk_backlog.len
is reset only at the very end of __release_sock().

Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach
sk_rcvbuf in normal conditions.

We should double sk->sk_rcvbuf contribution in the formula
to absorb bubbles in the backlog, which happen more often
for very fast flows.

This change maintains decent protection against abuses.

Fixes: c377411f2494 ("net: sk_add_backlog() take rmem_alloc into account")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240423125620.3309458-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 85d8688933f3cf1ebf6f84734ae34a13254106b6..0e7179a19e224a36f4b1986eff8e45119fe9703c 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1787,7 +1787,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
-       u32 limit, tail_gso_size, tail_gso_segs;
+       u32 tail_gso_size, tail_gso_segs;
        struct skb_shared_info *shinfo;
        const struct tcphdr *th;
        struct tcphdr *thtail;
@@ -1796,6 +1796,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
        bool fragstolen;
        u32 gso_segs;
        u32 gso_size;
+       u64 limit;
        int delta;
 
        /* In case all data was pulled from skb frags (in __pskb_pull_tail()),
@@ -1891,7 +1892,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
        __skb_push(skb, hdrlen);
 
 no_coalesce:
-       limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
+       /* sk->sk_backlog.len is reset only at the end of __release_sock().
+        * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach
+        * sk_rcvbuf in normal conditions.
+        */
+       limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1;
+
+       limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1;
 
        /* Only socket owner can try to collapse/prune rx queues
         * to reduce memory overhead, so add a little headroom here.
@@ -1899,6 +1906,8 @@ no_coalesce:
         */
        limit += 64 * 1024;
 
+       limit = min_t(u64, limit, UINT_MAX);
+
        if (unlikely(sk_add_backlog(sk, skb, limit))) {
                bh_unlock_sock(sk);
                __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP);